Neural network (NN)-based nonlinear equalizers have been shown effective for various types of short-reach direct detection systems. However, they work best for a certain channel condition and need to be trained again when the channel environment is changed, which hinders the efficient deployment of future optical switched data center networks. In this article, we propose transfer learning (TL)-aided feedforward neural networks (FNN) and recurrent neural networks (RNN) for nonlinear equalization in short-reach direct detection optical links, which enables a fast transition to new equalizers when the channel condition is changed. A 50-Gb/s 20-km pulse amplitude modulation (PAM)-4 optical link is experimentally demonstrated as the target system, and links of varying bit-rates and fiber lengths are selected as the source system. Experimental results show that TL could help reduce the number of epochs and training symbols of FNNs/RNNs required for nonlinear equalization in the target system, taking advantage of FNNs/RNNs trained for source systems. A reduction of 90%/87.5% in epochs and 62.5%/53.8% in training symbols is achieved with FNNs/RNNs transferred from the most similar source system. We also find that FNNs can be transferred to their corresponding RNNs for equalization in the target system, while TL from RNNs to FNNs cannot work properly. TL enables a fast transition between different NN-based equalizers, which is critical for future optical switched data center networks, where the optical links need to be dynamically reconfigured.

The computational complexity and system bit-error-rate (BER) performance of four types of neural-network-based nonlinear equalizers are analyzed for a 50-Gb/s pulse amplitude modulation (PAM)-4 direct-detection (DD) optical link. The four types are feedforward neural networks (F-NN), radial basis function neural networks (RBF-NN), auto-regressive recurrent neural networks (AR-RNN) and layer-recurrent neural networks (L-RNN). Numerical results show that, for a fixed BER threshold, the AR-RNN-based equalizers have the lowest computational complexity. Amongst all the nonlinear NN-based equalizers with the same number of inputs and hidden neurons, F-NN-based equalizers have the lowest computational complexity while the AR-RNN-based equalizers exhibit the best BER performance. Compared with F-NN or RNN, RBF-NN tends to require more hidden neurons with the increase of the number of inputs, making it not suitable for long fiber transmission distance. We also demonstrate that only a few tens of multiplications per symbol are needed for NN-based equalizers to guarantee a good BER performance. This relatively low computational complexity signifies that various NN-based equalizers can be potentially implemented in real time. More broadly, this paper provides guidelines for selecting a suitable NN-based equalizer based on BER and computational complexity requirements.

We propose a novel, to the best of our knowledge, cascade recurrent neural network (RNN)-based nonlinear equalizer for a pulse amplitude modulation (PAM)4 short-reach direct detection system. A 100 Gb/s PAM4 link is experimentally demonstrated over 15 km standard single-mode fiber (SSMF), using a 16 GHz directly modulated laser (DML) in C-band. The link suffers from strong nonlinear impairments which is mainly induced by the mixture of linear channel effects with square-law detection, the DML frequency chirp, and the device nonlinearity. Experimental results show that the proposed cascade RNN-based equalizer outperforms other feedforward or non-cascade neural network (NN)-based equalizers owing to both its cascade and recurrent structure, showing the great potential to effectively tackle the nonlinear signal distortion. With the aid of a cascade RNN-based equalizer, a bit-error rate (BER) lower than the 7% hard-decision forward error correction (FEC) threshold can be achieved when the receiver power is larger than 5 dBm. Compared with traditional non-cascade NN-based equalizers, the training time could also be reduced by half with the help of the cascade structure.

With the rapid development of machine learning technologies in recent years, different types of neural network (NN)-based equalizers have been proposed and proved to be efficient digital signal processing tools to deal with the nonlinear impairments in short-reach direct detection optical interconnects. However, one major concern for these NN-based equalizers is their computational complexity (CC), since only a few tens of multiplications per symbol can be practically handled considering real-time implementation. In this paper, we propose an NN-based multi-symbol equalization scheme inspired by multi-task learning. Compared with traditional single-output NN-based equalizers, the CC can be significantly reduced with the help of the proposed scheme. A 50-Gb/s 25-km pulse amplitude modulation (PAM)-4 direct detection optical link is experimentally carried out and 3 different types of NNs, i.e., feedforward NN (FNN), cascade FNN (C-FNN), and recurrent NN (RNN), are employed for the proposed multi-symbol equalization scheme. Experimental results show that a maximum CC reduction of 43.2%/41.1%/44.0% can be achieved with FNN/C-FNN/RNN-based multi-symbol equalization to achieve their best performance, compared with the corresponding single-output NNs. The best performance of the proposed and the traditional FNN/C-FNN-based schemes are the same, while the RNN-based scheme sacrifices a slight system performance. Aided by multi-symbol equalization, the CC needed to recover 1 symbol for various NNs can all be reduced to about a few tens of multiplications, indicating the feasibility of real-time implementation of these NN-based equalizers.

Quantum key distribution (QKD) is a secure communication method for sharing symmetric cryptographic keys based on the principles of quantum physics. Its integration into the fiber-optic network infrastructure is important for ensuring privacy in optical communications. Multi-core fibers (MCFs), the likely building blocks of future high-capacity optical networks, offer new opportunities for such integration. Here, we experimentally demonstrate, for the first time, the coexistence of discrete-variable QKD and high-throughput classical communication in the C-band over a field-deployed MCF with industry standard cladding diameter of 125 μm. Specifically, we demonstrate successful secure-key establishment in one core of a 25.2-km uncoupled-core MCF, while simultaneously loading the remaining three cores with full C-band counter-propagating classical traffic at an aggregate net rate of 110.8 Tb/s. By proposing and experimentally validating an improved analytical model for inter-core spontaneous Raman scattering noise, we find that this configuration is optimal for our deployed MCF link as it is immune to four-wave mixing, that becomes relevant when the quantum and classical signals are propagating in the same direction. Our findings make an important step forward in demonstrating the integration of QKD and classical transmission in uncoupled-core multi-core fibers for next-generation optical communication networks.

There has been renewed interest in coherent detection to provide high spectral efficiency transmission for short-reach optical interconnects. However, the expensive high-stable laser sources may preclude its potential application. To balance the high performance and low cost for short-reach optical networks, the self-coherent homodyne receiver has been investigated, where the dual-polarization (DP) signal and the remote local oscillator (LO) originating from the same laser source co-propagate over a duplex fiber, enabling a remarkable tolerance of laser linewidth. However, the fast evolution of the state of polarization (SOP) of remotely delivered LO becomes problematic for self-coherent homodyne detection systems. To combat the polarization wandering of the remote LO, the complicated adaptive/automatic polarization controller (APC) has been deployed with only up to a few hundred rad/s polarization tracking speed. In this paper, we propose a complementary polarization-diversity coherent receiver (C-PDCR) for self-coherent homodyne detection using remote LO. The proposed C-PDCR features rapid polarization tracking for remote LO utilizing electronic digital signal processing (DSP). The robustness of the proposed C-PDCR is verified and demonstrated with a 1.08-Tb/s line rate (net rate 769.4 Gb/s over 45-GHz electrical bandwidth) using DP PCS-256QAM signal under rapid polarization rotation rate up to 314 krad/s in the experiment, which is more than 3-orders improvement of magnitude compared to the prior reports.